As algorithms are increasingly used to make important decisions pertaining to individuals, algorithmic discrimination is becoming a prominent concern. The seminal work of Dwork et al. [ITCS 2012] introduced the notion of individual fairness (IF): given a task-specific similarity metric, every pair of similar individuals should receive similar outcomes. In this work, we study fairness when individuals have diverse preferences over the possible outcomes. We show that in such settings, individual fairness can be too restrictive: requiring individual fairness can lead to less-preferred outcomes for the very individuals that IF aims to protect (e.g. a protected minority group). We introduce and study a new notion of preference-informed individual fairness (PIIF), a relaxation of individual fairness that allows for outcomes that deviate from IF, provided the deviations are in line with individuals' preferences. We show that PIIF can allow for solutions that are considerably more beneficial to individuals than the best IF solution. We further show how to efficiently optimize any convex objective over the outcomes subject to PIIF, for a rich class of individual preferences. Motivated by fairness concerns in targeted advertising, we apply this new fairness notion to the multiple-task setting introduced by Dwork and Ilvento [ITCS 2019]. We show that, in this setting too, PIIF can allow for considerably more beneficial solutions, and we extend our efficient optimization algorithm to this setting.

Nowadays, the collection of user data is increasing exponentially. In this paper, we propose the idea of using an adversarial With this huge amount of data, many end users network which basically transforms a one-class deep struggle to find the most efficient way of interpreting it. One autoencoder (DAE), like the one used in [6], which learns of the most challenging tasks is to learn and detect unusual solely from normal data, into a two-class network that information patterns from the observed data. This kind of can classify normal and abnormal trajectories without the information can be thought as any form of observations need of setting manually a detection threshold. We use that do not follow the usual ones and that can also look a similar data structure and deep autoencoder model to suspicious. A popular application of anomaly detection is that of Roy and Bilodeau [5] proposed, but, instead of the detection of abnormal events in video surveillance [1]- computing the threshold value that separates normal from [4] in which the main purpose is to identify all the pixel abnormal data, we integrate the pretrained DAE into a deep groups that deviate from the ordinarily observed groups.

The non-storability of electricity makes it unique among commodity assets, and it is an important driver of its price behaviour in secondary financial markets. The instantaneous and continuous matching of power supply with demand is a key factor explaining its volatility. During periods of high demand, costlier generation capabilities are utilised since electricity cannot be stored and this has the impact of driving prices up very quickly. Furthermore, the non-storability also complicates physical hedging. Owing to these, the problem of joint price-quantity risk in electricity markets is a commonly studied theme. We propose using Gaussian Processes (GPs) to tackle this problem since GPs provide a versatile and elegant non-parametric approach for regression and time-series modelling. However, GPs scale poorly with the amount of training data due to a cubic complexity. These considerations suggest that knowledge transfer between price and load is vital for effective hedging, and that a computationally efficient method is required. To this end, we use the coregionalized (or multi-task) sparse GPs which addresses the aforementioned issues. To gauge the performance of our model, we use an average-load strategy as comparator. The latter is a robust approach commonly used by industry. If the spot and load are uncorrelated and Gaussian, then hedging with the expected load will result in the minimum variance position. Our main contributions are twofold. Firstly, in developing a coregionalized sparse GP-based approach for hedging. Secondly, in demonstrating that our model-based strategy outperforms the comparator, and can thus be employed for effective hedging in electricity markets.

Adam is a popular variant of the stochastic gradient descent for finding a local minimizer of a function. The objective function is unknown but a random estimate of the current gradient vector is observed at each round of the algorithm. This paper investigates the dynamical behavior of Adam when the objective function is non-convex and differentiable. We introduce a continuous-time version of Adam, under the form of a non-autonomous ordinary differential equation (ODE). The existence and the uniqueness of the solution are established, as well as the convergence of the solution towards the stationary points of the objective function. It is also proved that the continuous-time system is a relevant approximation of the Adam iterates, in the sense that the interpolated Adam process converges weakly to the solution to the ODE.

This paper reports on a novel formulation and evaluation of visual odometry from RGB-D images. Assuming a static scene, the developed theoretical framework generalizes the widely used direct energy formulation (photometric error minimization) technique for obtaining a rigid body transformation that aligns two overlapping RGB-D images to a continuous formulation. The continuity is achieved through functional treatment of the problem and representing the process models over RGB-D images in a reproducing kernel Hilbert space; consequently, the registration is not limited to the specific image resolution and the framework is fully analytical with a closed-form derivation of the gradient. We solve the problem by maximizing the inner product between two functions defined over RGB-D images, while the continuous action of the rigid body motion Lie group is captured through the integration of the flow in the corresponding Lie algebra. Energy-based approaches have been extremely successful and the developed framework in this paper shares many of their desired properties such as the parallel structure on both CPUs and GPUs, sparsity, semi-dense tracking, avoiding explicit data association which is computationally expensive, and possible extensions to the simultaneous localization and mapping frameworks. The evaluations on experimental data and comparison with the energy-based formulation of the problem confirm the effectiveness of the proposed technique, especially, when the lack of structure and texture in the environment is evident.

Advertisements (ads) often contain strong affective content to capture viewer attention and convey an effective message to the audience. However, most computational affect recognition (AR) approaches examine ads via the text modality, and only limited work has been devoted to decoding ad emotions from audiovisual or user cues. This work (1) compiles an affective ad dataset capable of evoking coherent emotions across users; (2) explores the efficacy of content-centric convolutional neural network (CNN) features for AR vis-\~a-vis handcrafted audio-visual descriptors; (3) examines user-centric ad AR from Electroencephalogram (EEG) responses acquired during ad-viewing, and (4) demonstrates how better affect predictions facilitate effective computational advertising as determined by a study involving 18 users. Experiments reveal that (a) CNN features outperform audiovisual descriptors for content-centric AR; (b) EEG features are able to encode ad-induced emotions better than content-based features; (c) Multi-task learning performs best among a slew of classification algorithms to achieve optimal AR, and (d) Pursuant to (b), EEG features also enable optimized ad insertion onto streamed video, as compared to content-based or manual insertion techniques in terms of ad memorability and overall user experience.

Humans and most animals can learn new tasks without forgetting old ones. However, training artificial neural networks (ANNs) on new tasks typically cause it to forget previously learned tasks. This phenomenon is the result of "catastrophic forgetting", in which training an ANN disrupts connection weights that were important for solving previous tasks, degrading task performance. Several recent studies have proposed methods to stabilize connection weights of ANNs that are deemed most important for solving a task, which helps alleviate catastrophic forgetting. Here, drawing inspiration from algorithms that are believed to be implemented in vivo, we propose a complementary method: adding a context-dependent gating signal, such that only sparse, mostly non-overlapping patterns of units are active for any one task. This method is easy to implement, requires little computational overhead, and allows ANNs to maintain high performance across large numbers of sequentially presented tasks when combined with weight stabilization. This work provides another example of how neuroscience-inspired algorithms can benefit ANN design and capability.

A group of Google employees have called for the removal of a rightwing thinktank leader from the company's new artificial intelligence council, citing her anti-LGBT and anti-immigrant record. Employees published a letter on Monday criticizing the appointment of Kay Coles James, the president of the Heritage Foundation, to Google's newly formed advisory council for "the responsible development of AI". James has a history of fighting trans rights and LGBT protections, and has advocated for Donald Trump's proposed border wall. "In selecting James, Google is making clear that its version of'ethics' values proximity to power over the wellbeing of trans people, other LGBTQ people and immigrants," the employees wrote in the letter, which was published online and shared internally at the company. "Such a position directly contravenes Google's stated values."

Jefferson Graham takes a look at two products that bring Alexa and voice-activated controls to the auto, Garmin Speak and Roav Viv. LOS ANGELES -- "Alexa, what music should I listen to?" It's an interesting question that follows up with Amazon's Alexa asking follow-ups, one of the few times the personal assistant gets really conversational and makes suggestions. Alexa, via Amazon Music, gave me options: the late, legendary gypsy guitarist Django Reinhardt or singers Adele or James Taylor. I went for Django, and with that, my personal DJ robot had followed through successfully, finding three artists I love. Such it is with music commands for personal assistants.

It can't dribble, let alone slam dunk, but Toyota's basketball robot hardly ever misses a free throw or a 3-pointer. The 207-centimeter-tall (6 feet 10-inches) machine made five of eight 3-point shots in a demonstration in a Tokyo suburb Monday, a ratio its engineers say is worse than usual. Toyota Motor Corp.'s robot, called Cue 3, computes a three-dimensional image where the basket is, using sensors on its torso, and adjusts motors inside its arm and knees to give the shot the right angle and propulsion for a swish. Efforts in developing human-shaped robots underline a global shift in robotics use from pre-programmed mechanical arms in limited situations like factories to functioning in the real world with people. The 2017 version of the robot was designed to make free throws.